Skip to content
AI News HubLIVE
Original source2 min read

FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

Summary

FlowPRO proposes a reward-free offline reinforced fine-tuning framework for flow-matching Vision-Language-Action (VLA) models. Its core algorithm RPRO combines a contrastive optimizer with an explicit proximal regularizer to eliminate reward hacking. Using a teleoperated intervention-and-rollback paradigm to collect paired trajectories, combined with smooth interpolation and batch mixing, it achieves dense per-state supervision. On four long-horizon bimanual tasks, FlowPRO achieves the highest success rate, outperforming four baselines.

SourcearXiv RoboticsAuthor: Yihao Wu, He Zhang, Junbo Tan, Xueqian Wang, Zhengyou Zhang
FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.05468] FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

[Submitted on 3 Jun 2026]

Title:FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization

View a PDF of the paper titled FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization, by Yihao Wu and 4 other authors

View PDF HTML (experimental)

Abstract:Post-training Vision-Language-Action (VLA) models into policies that can be reliably deployed on real robots remains a major bottleneck. SFT and DAgger exploit failure signals only indirectly, and reward-based RL is bottlenecked by the difficulty of real-world reward design and of training reliable critics. We present FlowPRO, a reward-free offline reinforced fine-tuning framework for flow-matching VLAs. Algorithmically, we propose RPRO (Robotic Flow-matching Proximalized Preference Optimization), a preference-optimization objective tailored to the flow-matching action head of VLA models. RPRO pairs a contrastive optimizer with an explicit proximal regularizer that anchors the absolute magnitude of the implicit reward, thereby eliminating the reward-hacking failure mode of plain Flow-DPO. On the data side, a teleoperated intervention-and-rollback paradigm produces naturally paired positive and negative trajectories $(\tau^w, \tau^l)$ on a real robot from a single operator action; a Smooth Interpolation procedure, combined with batch mixing, then converts these sparse corrections into dense per-state supervision while preserving the base policy's capabilities. On four long-horizon bimanual tasks, FlowPRO attains the highest success rate, outperforming four representative baselines, and ablations confirm the contribution of each loss component.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2606.05468 [cs.RO]

(or arXiv:2606.05468v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2606.05468

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: YiHao Wu [view email] [v1] Wed, 3 Jun 2026 21:47:43 UTC (6,828 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled FlowPRO: Reward-Free Reinforced Fine-Tuning of Flow-Matching VLAs via Proximalized Preference Optimization, by Yihao Wu and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.RO

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • Proposes FlowPRO, a reward-free offline RL fine-tuning framework for flow-matching VLAs.
  • RPRO algorithm suppresses reward hacking via proximal regularization, improving preference optimization stability.
  • Teleoperated intervention-and-rollback paradigm with smooth interpolation generates dense supervision signals.
  • Achieves highest success rate on long-horizon bimanual tasks; ablations confirm component contributions.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Models